Consumer insights analysis using word embeddings
In one embodiment, a method includes receiving a request to generate a two-dimensional visualization of public sentiments regarding a particular subject, where the request includes an input n-gram representing the particular subject, constructing a first corpus of text by collecting text containing the input n-gram from a plurality of user-created content objects in the online social network, identifying a list of unique n-grams appearing in the first corpus of text, generating a table comprising unique n-grams in the list and their corresponding word vectors using a word embedding model, condensing the d-dimensional word vectors in the table into a two-dimensional word vectors; and sending, as a response to the request, instructions to display n-grams in the table on a two-dimensional display space, where each n-gram is placed at a location of the corresponding condensed word vector.
1. A method comprising:
by a computing device in an online social network, receiving a request to generate a two-dimensional visualization of public sentiments regarding a particular subject, wherein the request comprises an input n-gram representing the particular subject, and wherein the request comprises one or more conditions characterizing an audience;
by the computing device, identifying users of the online social network who satisfy the one or more conditions;
by the computing device, constructing a first corpus of text by collecting text containing the input n-gram from a plurality of content objects in the online social network created by the identified users;
by the computing device, identifying a list of unique n-grams appearing in the first corpus of text;
by the computing device, determining, using a word embedding model, a d-dimensional word vector corresponding for each of the unique n-grams in the list, wherein the word embedding model was trained using a second corpus of text collected from a plurality of content objects in the online social network created by the identified users as training data, wherein each of the word vectors represents a semantic context of a corresponding n-gram as a point in a d-dimensional embedding space;
by the computing device, condensing the d-dimensional word vectors corresponding to the unique n-grams in the list into two-dimensional word vectors; and
by the computing device, sending, as a response to the request, instructions to display the n-grams in the list on a two-dimensional display space, wherein each n-gram is placed at a location of the corresponding condensed word vector.
2. The method of claim 1 , wherein the word embedding model is a word2vec model.
3. The method of claim 1 , wherein the condensing the d-dimensional word vectors corresponding to the unique n-grams in the list into the two-dimensional word vectors comprises performing a t-distributed Stochastic Neighbor Embedding (t-SNE) dimensionality reduction on the word vectors.
4. The method of claim 1 , further comprises determining a Term Frequency-Inverse Document Frequency (TF-IDF) ranking of the n-grams in the list.
5. The method of claim 4 , wherein the instructions comprise instructions to adjust a font size or font color for each n-gram based at least on a respective TF-IDF rank assigned to the n-gram.
6. The method of claim 4 , wherein, if a number of n-grams in the list exceeds a threshold, the instructions comprise instructions to display only n-grams with TF-IDF ranks higher than a pre-determined value.
7. The method of claim 1 , wherein the content objects were created within a pre-determined period of time.
8. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
receive a request to generate a two-dimensional visualization of public sentiments regarding a particular subject, wherein the request comprises an input n-gram representing the particular subject, and wherein the request comprises one or more conditions characterizing an audience;
identify users of the online social network who satisfy the one or more conditions;
construct a first corpus of text by collecting text containing the input n-gram from a plurality of content objects in the online social network created by the identified users;
identify a list of unique n-grams appearing in the first corpus of text;
determine, using a word embedding model, a d-dimensional word vector corresponding for each of the unique n-grams in the list, wherein the word embedding model was trained using a second corpus of text collected from a plurality of content objects in the online social network created by the identified users as training data, wherein each of the word vectors represents a semantic context of a corresponding n-gram as a point in a d-dimensional embedding space;
condense the d-dimensional word vectors corresponding to the unique n-grams in the list into two-dimensional word vectors; and
send, as a response to the request, instructions to display the n-grams in the list on a two-dimensional display space, wherein each n-gram is placed at a location of the corresponding condensed word vector.
9. The media of claim 8 , wherein the word embedding model is a word2vec model.
10. The media of claim 8 , wherein the condensing the d-dimensional word vectors corresponding to the unique n-grams in the list into the two-dimensional word vectors comprises performing a t-distributed Stochastic Neighbor Embedding (t-SNE) dimensionality reduction on the word vectors.
11. The media of claim 8 , wherein the software is further operable when executed to determine a Term Frequency-Inverse Document Frequency (TF-IDF) ranking of the n-grams in the list.
12. The media of claim 11 , wherein the instructions comprise instructions to adjust a font size or font color for each n-gram based at least on a respective TF-IDF rank assigned to the n-gram.
13. The media of claim 11 , wherein, if a number of n-grams in the list exceeds a threshold, the instructions comprise instructions to display only n-grams with TF-IDF ranks higher than a pre-determined value.
14. The media of claim 8 , wherein the content objects were created within a pre-determined period of time.
15. A system comprising:
one or more processors; and
one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to:
receive a request to generate a two-dimensional visualization of public sentiments regarding a particular subject, wherein the request comprises an input n-gram representing the particular subject, and wherein the request comprises one or more conditions characterizing an audience;
identify users of the online social network who satisfy the one or more conditions;
construct a first corpus of text by collecting text containing the input n-gram from a plurality of content objects in the online social network created by the identified users;
identify a list of unique n-grams appearing in the first corpus of text;
determine, using a word embedding model, a d-dimensional word vector corresponding for each of the unique n-grams in the list, wherein the word embedding model was trained using a second corpus of text collected from a plurality of content objects in the online social network created by the identified users as training data, wherein each of the word vectors represents a semantic context of a corresponding n-gram as a point in a d-dimensional embedding space;
condense the d-dimensional word vectors corresponding to the unique n-grams in the list into two-dimensional word vectors; and
send, as a response to the request, instructions to display the n-grams in the list on a two-dimensional display space, wherein each n-gram is placed at a location of the corresponding condensed word vector.